model-routing

model-routing is a skill for Claude Code, Codex from alebgl77/tierdecay. It costs 72 tokens per session (990 once invoked), scanned A, original, MIT.

A task-routing guide that assigns coding work to one of four model levels based on complexity, risk, and the project's past results.

In plain words
What is it for?
It helps plan multi-step work, choose an executor, write task instructions, and retry work at a higher model level when needed.
Why use it?
It reduces guesswork when choosing between faster, cheaper models and models suited to difficult or risky work. It also defines when to escalate a failed task.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/alebgl77/tierdecay/model-routing
Any agent
npx skills add alebgl77/tierdecay --skill model-routing
Clone the repo
git clone --depth 1 https://github.com/alebgl77/tierdecay

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for model-routing

README.md
[![agentmods](https://agentmods.dev/badge/skills/alebgl77/tierdecay/model-routing.svg)](https://agentmods.dev/skills/alebgl77/tierdecay/model-routing)
Your own site
<a href="https://agentmods.dev/skills/alebgl77/tierdecay/model-routing"><img src="https://agentmods.dev/badge/skills/alebgl77/tierdecay/model-routing.svg" alt="Measured on agentmods" height="20"></a>
Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 990 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00072 $0.00990
Opus 5 $0.00036 $0.00495
Sonnet 5 $0.00014 $0.00198
Haiku 4.5 $0.00007 $0.00099

Measured 3d ago against content hash 9fe6585672da, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

model-routing scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

adapters/claude-code/.claude/skills/model-routing/SKILL.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Model Routing

0. Ledger pre-check — posterior beats prior

Before scoring anything, read .claude/routing-ledger.md, in this order:

  • Class has a live repo-playbook entry (not quarantined, floor not reached) → dispatch one tier below the entry's provenance as a PROBE, entry quoted in the brief (tier-decay §3). A live entry outranks PRIORS — this is what keeps decay iterating.
  • Else task matches a class in PRIORS (≥3 logged rows) → use its empirical default tier, skip the rubric.
  • Otherwise → score below. The rubric is only the cold-start prior.

1. Scoring rubric

Score the task on four axes; sum the points.

Axis 0 1 2 3
Spec ambiguity fully specified minor gaps requires design decisions
Reasoning depth mechanical standard logic multi-constraint / algorithmic novel algorithm, proof-like
Blast radius 1 file 2–5 files >5 files or shared/core module
Risk surface cosmetic user-visible bug data / perf / concurrency security, money, irreversible

Route:

  • 0–3 → [T1] executor (fast tier)
  • 4–6 → [T2] heavy-executor (strong workhorse)
  • ≥7, or any axis at its maximum → [T3]: the frontier tier produces the spec (main thread, or oracle SOLVE) → heavy-executor implements it → oracle REVIEWs the diff.

Tie-breaks: strong existing test coverage → down one tier. Critical path, or first task in an unfamiliar area → up one tier.

2. Fast lane (skip scoring when obvious)

  • [T1] boilerplate, CRUD, tests of specified behavior, docs, renames, config, dependency bumps, bugfix with a clean repro.
  • [T2] cross-module refactor, async/concurrency, migrations, perf work, gnarly bug without repro, implementing an already-designed API.
  • [T3] architecture choices, novel algorithms, security-sensitive design, cross-cutting invariants — anything where being wrong is expensive to discover.

Read the full file on GitHub · 87 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 87 lines · 72 tokens per session scan A 9fe6585672da

Subscribe to this mod's changes

model-routing is a skill published in the GitHub repository alebgl77/tierdecay (1 stars, last pushed 1mo ago), licensed MIT. It adds 72 tokens to every session and 990 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.